First look - Muse by Google AI/Research - Launched 2/Jan/2023 - (3B + 4.6B T5-XXL) - Google Muse

First look - Riffusion (Dec/2022) - Text-to-image-to-music (Similar output to Jukebox, SymphonyNET)

AI Art generation with Becky Robbins - LifeArchitect.ai LIVE (DALL-E 2)

First look - ERNIE-ViLG 2.0 by Baidu - Launched Oct/2022 - 'Better' than DALL-E 2 & Stable Diffusion

First look - Google UniTune (fine-tuned Imagen) by Google Research/AI - Launched Oct/2022

First look - Google DreamBooth (fine-tuned Imagen) by Google Research/AI - Launched Aug/2022

Integrated AI - Savants & Stable Diffusion with 'best of' examples (prodigies, DALL-E 2, LAION)

First look - NUWA-Infinity by Microsoft Research Asia - Text-to-image - Better than DALL-E 2 [4K]

First look - Parti by Google AI/Research/Brain - Launched Jun/2022 - (20B) [+ prodigies, Kurzweil]

First look - CogView2 by Tsinghua University & BAAI - Launched Jun/2022 (480x480+ resolution only)

First look - Imagen by Google AI/Research/Brain - Launched May/2022 - (2B + 1B + 4.6B T5-XXL)

First look - 1,000 Robots by OpenAI Design Director - DALL-E 2 (3.5B) by OpenAI - Launched Apr/2022

First look - GLIDE (300M) by OpenAI - Text to image, similar to CLIP, DALL-E, Launched Dec/2021

First look: Stable Diffusion's Top 10 Datasets

First look - Midjourney v5 - Text-to-image - State-of-the-art model (Mar/2023) relaxing, calm...

The Memo header image rendered to video by Kaiber.ai (Apr/2023)

First look - RAPHAEL by HKU & SenseTime - Launched May/2023 - Higher quality than SD XL, DALL-E 2

First look - Suno.ai - Aug/2023 - Text-to-song (realistic audio, rap, lyrics, chirp, Leta AI, GPT-4)

First look - OpenAI DALL-E 3 - Text-to-image - Better than Midjourney v5 - Sep/2023 State-of-the-art

Movies by AI - DALL-E 3 - The Minions and their road to Champions League glory

22/Feb/2024 - Stable Diffusion 3 - LifeArchitect.ai